English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Dynamic traversal of uneven terrain is a major objective in the field oflegged robotics. The most recent model predictive control approaches for thesesystems can generate robust dynamic motion of short duration; however, planningover a longer time horizon may be necessary when navigating complex terrain. Arecently-developed framework, Trajectory Optimization for Walking Robots(TOWR), computes such plans but does not guarantee their reliability on realplatforms, under uncertainty and perturbations. We extend TOWR with analyticalcosts to generate trajectories that a state-of-the-art whole-body trackingcontroller can successfully execute. To reduce online computation time, weimplement a learning-based scheme for initialization of the nonlinear programbased on offline experience. The execution of trajectories as long as 16footsteps and 5.5 s over different terrains by a real quadruped demonstratesthe effectiveness of the approach on hardware. This work builds toward anonline system which can efficiently and robustly replan dynamic trajectories.

Reliable Trajectories for Dynamic Quadrupeds using Analytical Costs and Learned Initializations